Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add openshift-online/gcp-hcp --skill fix-implementation-plan-driftsgit clone --depth 1 https://github.com/openshift-online/gcp-hcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/openshift-online/gcp-hcp/fix-implementation-plan-drifts)<a href="https://agentmods.dev/skills/openshift-online/gcp-hcp/fix-implementation-plan-drifts"><img src="https://agentmods.dev/badge/skills/openshift-online/gcp-hcp/fix-implementation-plan-drifts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openshift-online/gcp-hcp/fix-implementation-plan-drifts"><img src="https://agentmods.dev/badge/skills/openshift-online/gcp-hcp/fix-implementation-plan-drifts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.01218 |
| Opus 5 | $0.00032 | $0.00609 |
| Sonnet 5 | $0.00013 | $0.00244 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
fix-implementation-plan-drifts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Implementation Plan Drifts
Overview
Implementation plans are living documents. When code ships, the plan should reflect what was built. This skill detects the gap and determines whether to update the plan or flag the code for review.
When to Use
- A feature PR merged that implements part of a plan
- A Jira epic moved to Done but the plan wasn't updated
- Reviewing a plan before starting new work on top of it
- Code review flagged something that contradicts the plan
How to Start
- Ask the user: verify a specific plan or all plans?
- Ask which repos to verify against. Plans often span multiple repositories. The user can choose the current repo, a specific repo, or all repos referenced in the plan. Default to the current repo.
- Use the cross-repo map from the
gcp-hcp-architectureskill to identify which repo owns each component. If the plan references repos beyond the user's selection, list them and ask if the user wants to include them.
What Is Drift
Drift is the gap between what the plan says and what the code does. It goes both ways:
- Plan drifted from code — the code evolved but the plan was never updated. Fix: update the plan.
- Code drifted from plan — the implementation deviated from the planned design, especially when it breaks architectural invariants or core principles. Fix: flag for team review.
Focus on meaningful differences — API contracts, behavior, architecture. Don't nitpick formatting or stylistic choices.
Drift Categories
For each plan, verify these against actual code:
API surface — types, structs, or fields don't match actual definitions. Grep for every type and field mentioned. Compare names, tags, and markers. (e.g., plan references GCPNetworkSpec but code renamed it to GCPNetworkConfig)
Behavior — controller reconciliation logic, ownership patterns, or data flow differ from actual code. Read the actual reconcilers. (e.g., plan describes credentials managed in HO layer but code manages them in CPO)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 107 lines · 64 tokens per session scan A f3bf59d22127
fix-implementation-plan-drifts is a skill published in the GitHub repository openshift-online/gcp-hcp (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,218 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…